Miril DroneVLM 2B 2 needs about 4.5 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 3.0 GB (Q2_K) to 9.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.
Miril DroneVLM 2B 2 – a 4.63B‑parameter aerial vision‑language model
Miril DroneVLM 2B 2 is a 4.63B‑parameter model built on the gemma4 architecture. It can reason, use tools, and process vision inputs. The model is released under the apache‑2.0 license and supports a 131072‑token context window.
Good at
- Aerial image understanding
- Structured JSON output
- Reasoning over visual scenes
Limits
- No vision support on older hardware
- Large VRAM requirement for full precision
- Limited to text‑only inference on low‑memory devices
Best for
- Drone delivery coordination
- First‑response scene analysis
- Infrastructure inspection
Who it’s for. Developers building drone‑based perception systems. The model is suitable for edge‑oriented research and practical applications in civilian drone operations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.0 GB | 4.1 GB | Fits | Get file → | |
| Q3_K_S | 3.1 GB | 4.2 GB | Fits | Get file → | |
| Q3_K_M | 3.2 GB | 4.3 GB | Fits | Get file → | |
| Q3_K_L | 3.3 GB | 4.4 GB | Fits | Get file → | |
| IQ4_XS | 3.3 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_S | 3.4 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_M | 3.4 GB | 4.5 GB | Fits | Get file → | |
| Q5_K_S | 3.6 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.6 GB | 4.7 GB | Fits | Get file → | |
| Q6_K | 3.8 GB | 4.9 GB | Fits | Get file → | |
| Q8_0 | 4.9 GB | 6.0 GB | Fits | Get file → | |
| F16 | 9.3 GB | 10.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (3.42 GB) or Q5_K_M (3.62 GB). For 12 GB VRAM, Q6_K (3.83 GB) or Q8_0 (4.95 GB) are suitable. Full precision F16 requires 9.27 GB and 10.4 GB memory at 8 k context.
What GPU do you need for Miril DroneVLM 2B 2?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (9.3 GB file, about 10.4 GB in use).
Which Miril DroneVLM 2B 2 quant should you choose?
Q4_K_M is the usual starting point for Miril DroneVLM 2B 2: it balances file size and quality well. Here it is a 3.4 GB file.
The Q8_0 file is 4.9 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 3.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Miril DroneVLM 2B 2
How much VRAM does Miril DroneVLM 2B 2 need?
About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Miril DroneVLM 2B 2 on an 8 GB GPU?
Yes, with Q8_0: the 4.9 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Miril DroneVLM 2B 2 GGUF?
It depends on the quant: Q2_K is 3.0 GB, Q3_K_S is 3.1 GB, Q3_K_M is 3.2 GB, Q3_K_L is 3.3 GB, IQ4_XS is 3.3 GB, Q4_K_S is 3.4 GB and 6 more.
What context length does Miril DroneVLM 2B 2 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.
Where can I download Miril DroneVLM 2B 2 GGUF?
The files are on Hugging Face in the mradermacher/Miril-DroneVLM-2B-2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Miril DroneVLM 2B 2 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Miril DroneVLM 2B 2 on 8 GB VRAM?
Yes, using Q4_K_M or Q5_K_M quants. They fit within 8 GB VRAM and use about 4.5–4.7 GB memory at 8 k context.
Does the model support vision input?
Yes, it processes images and returns JSON responses such as captions, answers, locations, or points.
What license applies to this model?
The model is released under the apache‑2.0 license.